{
  "id": 16705001,
  "title": "Audit Where Hacks Pay: Budgeted Strong-Verifier Audits Against Reward Hacking in GRPO",
  "url": "https://urgent.news/2026/10/26/audit-where-hacks-pay-budgeted-strong-verifier-audits-against-reward",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-10-26T16:38:14.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.35716v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Reinforcement learning with verifiable rewards trains on cheap checks, such as unit tests, that a policy can learn to game, while a stronger check is too expensive to run on every rollout. We study how to spend a limited strong-verifier budget in GRPO, separating which weakly passing rollouts to audit from what reward a caught hack receives. At a fixed policy state with centered advantages, the…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}